"National Rail" matching MCP servers:

Adds a responsible-AI safety layer to any agent by exposing RAIL Score's evaluation, agent-guardrail, and compliance capabilities as MCP tools, enabling content scoring, injection detection, tool call evaluation, and DPDP compliance checks.

Enables AI agents to read and send email, handle attachments and manage calendar invitations through their own IMAP/SMTP mailboxes, with per-mailbox sender and recipient allow lists and automatic HTML-to-Markdown conversion. It runs as a single self-hosted Docker container, exposing the same tools over MCP and REST.

Enables an AI assistant to list, search, and read email over IMAP without marking messages as read, and to create and revise reply drafts that you review before sending. It runs with least privilege, keeping the app password in an OS keychain or password store and never sending, deleting, or moving anything.

Enables MCP clients to connect to miyoushe and HoYoLAB accounts with QR login, encrypted credential storage, multi-account and game role discovery, daily notes for Star Rail, Genshin Impact, and Zenless Zone Zero, plus stamina alert checks with deduplication.

An MCP server that brings NIST National Vulnerability Database (NVD) intelligence directly into Claude, enabling CVE lookup, product search, and prioritized risk assessment via natural language.

The deterministic fact-verification layer for AI agents. Validates the structured facts an agent emits — IBANs, payment cards, VAT and national tax IDs, crypto and bank addresses, domains, emails, phone numbers, securities and academic identifiers, plus dates, currencies and holidays — against checksums and curated authoritative data, not guesses.

Enables local access to multiple email accounts across Gmail OAuth, IMAP/SMTP, and Proton Mail Bridge, requiring an explicit account ID for each action. It supports listing folders, searching and reading messages, and preparing or sending mail while keeping credentials in the operating system credential store.

Policy-gated agent spend with signed receipts and rail-extract audit: a fail-closed gate issues a COSE receipt for every allowed payment, and the audit reconciles those receipts against a rail extract so a settlement with no receipt is named rather than assumed. It settles on a mock rail, holding no wallet and signing no transaction.

PII sanitization layer for autonomous AI agent pipelines. Detects and redacts emails, phone numbers, national IDs, private keys, and financial data before text reaches LLMs. Supports EN, ES (LATAM), PT (BR/PT), DE, JA.

Enables ChatGPT and Codex to securely inspect a QQ Mail mailbox through read-only tools for identity, connection status, unread messages, search, and message reading. Uses OAuth 2.1/PKCE and IMAP without sending, deleting, moving, or marking mail.

Enables running AI coding agents and MCP servers inside an OS-level least-privilege sandbox that hides credentials and blocks network access by default, with tool firewalling, rug-pull protection, audit logging, and boundary verification.

Enables AI agents to search, retrieve, and analyze vulnerability data from the NIST National Vulnerability Database through a comprehensive Model Context Protocol server.

Zero-trust safety & settlement rail for autonomous AI agents. Sub-10ms deterministic guardrails, secret leak defense, bounded wallet controls, and on-chain Proof-of-Safety attestations via x402.

Provides offline access to Spanish national security framework (ENS) measures, enabling querying of Annex II, applicability matrices, and audit checklists for compliance assessments.

A Model Context Protocol server that retrieves CVE information from the National Vulnerability Database, allowing AI models to access up-to-date vulnerability data.

A Model Context Protocol server implementation to query the NIST National Vulnerability Database (NVD) via its API.

Enables identity verification by checking name, address, and date of birth against national databases.

Enables agents to generate tamper-evident SHA-256 Merkle audit trails, produce logarithmic inclusion proofs, and verify integrity through a STDIO MCP interface.

Enables AI to verify KeyHalve-sealed documents from any platform. Verifies status, ciphertext integrity, rail attestation, time lock, and issuer trust without requiring decryption keys.

Deterministic AST vulnerability remediation and formal verification for AI coding assistants using Microsoft Z3 SMT logic.

Enables an MCP client to read, draft, organize, send, and delete email across multiple Gmail and Exchange Online/Outlook.com accounts, with per-account capability policies, recipient allowlists, confirmations, minimum OAuth scopes, and local audit logging.

This MCP server enables real-time injection fuzzing, exfiltration canary detection, least-privilege tool sandboxing, and cryptographic Merkle audit proofs for agent prompts, RAG context, and actions. It provides tamper-evident SHA-256 tree generation, logarithmic inclusion proofs, and verifiable integrity checks through MCP.

Enables real-time verification of Korean business registration status and KYB identity checks using official Korea National Tax Service data.

MCP server providing immutable audit logging, policy enforcement, and compliance reporting for AI agent workflows, enabling regulatory compliance and chain integrity verification.

Enables irreversible anonymisation of documents and spreadsheets (PDF, Word, PowerPoint, HTML, Excel, CSV) into consistent pseudonymised Markdown before they reach an AI, keeping names, national IDs, bank details and contact data unrecoverable. Runs as a free online HTTP endpoint needing no key, or locally with the full engine bundled so nothing leaves the machine.

Enables users to browse folders, list and search messages, read emails, and retrieve selected attachments through a private read-only MCP bridge with OAuth and safe HTML extraction.

Enables querying CVE vulnerability data from the NIST National Vulnerability Database, including CVE lookup, product/version search via CPE filters, CVSS severity scores, and recent high-severity disclosures.

Enables read-only inspection of a Zoho mailbox over a one-shot, outbound-only connection — listing accounts and folders, listing or searching messages, and retrieving message content and attachment metadata — plus bounded parsing of aggregate DMARC report attachments via a separate REST adapter. It performs no writes, sends, deletes, or read-marks, and requires a trusted private configuration envelope for pinned hosts, mailboxes, and credentials.

MCP server for searching NIST's National Vulnerability Database, enabling retrieval of recent CVEs, keyword/CPE/CWE searches, and detailed CVE information.

Provides read-only email access over a remote HTTP MCP endpoint, enabling agents to search mailboxes, read messages, and retrieve attachments from self-hosted IMAP accounts with OAuth-authenticated access.